A new energy vehicle after-sales data management system based on big data

Abstract

A new energy vehicle after-sales data management system based on big data relates to the technical field of data management. The invention relates to the following steps: obtaining vehicle data and constructing a vehicle after-sales model, dividing the vehicle after-sales model into different model sets, respectively obtaining corresponding influencing parameter sets and after-sales degrees according to spare parts in the same model set, constructing an after-sales evaluation model according to different influencing parameter sets and their after-sales degrees, obtaining an after-sales degree set and spare parts to be sold, obtaining geographic data of after-sales points and constructing an after-sales distribution map, obtaining after-sales data of after-sales points, providing users with optimal after-sales points and constructing navigation routes in combination with spare parts to be sold; the technical solution of the invention is conducive to deepening the management of after-sales data to the spare parts level, forming a targeted judgment mechanism for different spare parts, and facilitating accurate judgment of whether spare parts need after-sales service.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to an after-sales data management system for new energy vehicles based on big data. Background Art

[0002] The use of big data analysis technology to manage the after-sales data of new energy vehicles aims to comprehensively and efficiently manage and analyze the after-sales data of new energy vehicles through big data technology to meet the diverse needs of consumers and manufacturers. By integrating multi-dimensional data such as vehicle status, user behavior, and consumption habits, the system can provide users with personalized service recommendations and help manufacturers optimize after-sales service processes and improve service levels.

[0003] In the prior art, the management of after-sales related data of vehicles is mostly not intuitive and in-depth. The vehicle is often analyzed as a whole, and an overall parameter is obtained to reflect whether the vehicle needs after-sales service. This method ignores the differences between different spare parts. In the prior art, the judgment criteria for whether a vehicle and its spare parts need after-sales service are often fixed. This method ignores the differences between different vehicles. In view of the shortcomings of the prior art, the present invention provides a new energy vehicle after-sales data management system based on big data. Summary of the invention

[0004] The purpose of the present invention is to provide a new energy vehicle after-sales data management system based on big data.

[0005] The purpose of the present invention can be achieved through the following technical solutions: A new energy vehicle after-sales data management system based on big data, comprising the following modules:

[0006] Data collection module, used to obtain the user's vehicle data and build the corresponding vehicle after-sales model;

[0007] A data analysis module is used to divide the vehicle after-sales model into different model sets, obtain corresponding influencing parameter sets according to the spare parts in the same model set, and obtain the after-sales degree of the spare parts according to the influencing parameter sets;

[0008] The after-sales evaluation module is used to build an after-sales evaluation model for spare parts based on different influencing parameter sets and their corresponding after-sales degrees, obtain the user's after-sales degree set, obtain the spare parts to be sold based on the after-sales degree set, and generate corresponding after-sales signals;

[0009] The after-sales selection module is used to obtain the geographic data of after-sales points, build a corresponding after-sales distribution map, obtain the after-sales data of after-sales points, provide users with the best after-sales points in combination with the spare parts to be sold, and build a corresponding navigation route.

[0010] Furthermore, the process of obtaining the user's vehicle data and building the corresponding vehicle after-sales model includes:

[0011] Collect various vehicle data of users, including basic information, performance parameters, usage status, after-sales records, and spare parts information;

[0012] Digital twin technology is used to build a digital twin model of the vehicle based on basic information, performance parameters, and usage conditions. After-sales records and spare parts information are uploaded to the digital twin model for synchronization to obtain the vehicle after-sales model.

[0013] Furthermore, the vehicle after-sales model is divided into different model sets, and the process of obtaining corresponding influencing parameter sets according to the spare parts in the same model set includes:

[0014] The vehicle after-sales model includes different components, each component includes different spare parts, and the vehicle after-sales models including the same spare parts are included in the same model set;

[0015] The parts common to the same model set are used as the analysis parts of the model set, the replacement records and analysis nodes of the analysis parts in the after-sales model of a single vehicle in the model set are obtained, and the maintenance records and repair records of adjacent analysis nodes and their corresponding analysis sub-nodes are obtained;

[0016] Include the analysis subnodes between any two adjacent analysis nodes into an analysis set, and obtain the number of nodes in each analysis set and their corresponding node intervals and mileage intervals;

[0017] The influencing parameter set includes the number of nodes in each analysis set in different vehicle after-sales models in the same model set and their corresponding node intervals and mileage intervals, and the analysis parts and influencing parameter sets of each model set are obtained respectively.

[0018] Furthermore, the process of obtaining the after-sales degree of spare parts according to the influencing parameter set includes:

[0019] According to the number of nodes n and node interval S in a single analysis set in the influencing parameter set i , Mileage interval L i Get the local after-sales degree R of the analysis set b , i=1,2,…,n;

[0020]

[0021] is a preset fixed parameter, according to the local after-sales degree R of each analysis set in the same influencing parameter set bj , obtain the comprehensive after-sales degree R of the analyzed parts corresponding to the influencing parameter set z, j = 1, 2, ..., m, m is the total number of analysis sets in the influencing parameter set,

[0022]

[0023] The comprehensive after-sales degree of the analyzed parts and components corresponding to different influencing parameter sets are obtained respectively, and the after-sales degree is divided into a local after-sales degree and a comprehensive after-sales degree.

[0024] Furthermore, the process of constructing the after-sales evaluation model of spare parts according to different influencing parameter sets and their corresponding after-sales degrees includes:

[0025] Generate an after-sales evaluation set according to the number of nodes, node interval, mileage interval and corresponding local after-sales degree of different analysis sets in the influencing parameter set of a single spare part, and divide the after-sales evaluation set into a training set and a test set;

[0026] Construct a convolutional neural network, use different numbers of nodes, node intervals, and mileage intervals in the training set as input data of the convolutional neural network, use the corresponding local after-sales degree in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

[0027] The test set is used to verify the initial convolutional neural network model, and the initial convolutional neural network with a preset test error threshold is output as the after-sales evaluation model of a single spare part, and the after-sales evaluation models of each spare part are obtained respectively.

[0028] Furthermore, the process of obtaining a user's after-sales degree set, obtaining spare parts to be sold according to the after-sales degree set, and generating a corresponding after-sales signal includes:

[0029] Obtaining the current analysis set of each spare part in the user's vehicle after-sales model, wherein the current analysis set refers to all repair records and maintenance records from the latest replacement record to the present;

[0030] Input the number of nodes, node intervals, and mileage intervals in each current analysis set into the corresponding after-sales evaluation model to obtain the corresponding evaluated after-sales degree, and include the evaluated after-sales degree of each spare part into the user's after-sales degree set;

[0031] According to the comprehensive after-sales degree of a single spare part and the current analysis set, a corresponding after-sales degree threshold is set for it, and the mean of the number of nodes in each analysis set in the impact parameter set of the single spare part is taken as the standard node number Q z ;

[0032] Get the number of nodes Q in the current analysis set of this single component d , combined with its comprehensive after-sales service z Get the after-sales threshold R of the single spare part y;

[0033]

[0034] The evaluation of the after-sales degree of this single spare part is R p and after-sales threshold R y Comparison is performed to obtain corresponding spare parts to be sold, after-sales degree thresholds of various spare parts and their spare parts to be sold are obtained respectively, and corresponding after-sales signals are generated for feedback.

[0035] Furthermore, the process of obtaining geographic data of after-sales points and constructing a corresponding after-sales distribution map includes:

[0036] The after-sales point refers to a business place that can provide after-sales service for vehicles. The geographic data of all after-sales points in different regions are obtained, including the geographical location of each after-sales point and the traffic routes in different regions. GIS technology is used to construct after-sales distribution maps of different regions based on geographic data.

[0037] Furthermore, the process of obtaining after-sales data of after-sales points, providing users with the best after-sales points in combination with spare parts to be sold, and constructing corresponding navigation routes includes:

[0038] Obtain after-sales data of all after-sales outlets in different regions, including spare parts that can be provided by each after-sales outlet and their corresponding after-sales prices, and select the after-sales outlet that contains the user's spare parts to be provided and has the lowest after-sales price as the optimal after-sales outlet;

[0039] The user's vehicle location is obtained, the shortest navigation route is generated between the vehicle location and the optimal after-sales point in the after-sales distribution map, and the generated navigation route is fed back to the user.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] 1. The present invention can display the after-sales situation of the vehicle in the digital twin model by constructing a vehicle after-sales model. By incorporating the vehicle after-sales models containing the same spare parts into the same model set, it is beneficial to deepen the management of after-sales data to the spare parts level. By obtaining the influencing parameter set of each spare part in the same model set, the local after-sales degree and comprehensive after-sales degree of each spare part are obtained, and the after-sales evaluation model is constructed using the local after-sales degree, the current after-sales degree of the vehicle can be evaluated, thereby reflecting whether the vehicle spare parts need after-sales service;

[0042] 2. The present invention sets corresponding after-sales degree thresholds for different spare parts according to the real-time status of the vehicle, and can generate flexible after-sales degree thresholds based on the comprehensive after-sales degree combined with the current parameter set of the vehicle. On this basis, a targeted judgment mechanism can be formed for different spare parts, which is conducive to accurately judging whether the spare parts need after-sales service and providing users with the corresponding optimal after-sales point. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0044] like Figure 1 As shown, a new energy vehicle after-sales data management system based on big data includes the following modules:

[0045] Data collection module, used to obtain the user's vehicle data and build the corresponding vehicle after-sales model;

[0046] A data analysis module is used to divide the vehicle after-sales model into different model sets, obtain corresponding influencing parameter sets according to the spare parts in the same model set, and obtain the after-sales degree of the spare parts according to the influencing parameter sets;

[0047] The after-sales evaluation module is used to build an after-sales evaluation model for spare parts based on different influencing parameter sets and their corresponding after-sales degrees, obtain the user's after-sales degree set, obtain the spare parts to be sold based on the after-sales degree set, and generate corresponding after-sales signals;

[0048] The after-sales selection module is used to obtain the geographic data of after-sales points, build a corresponding after-sales distribution map, obtain the after-sales data of after-sales points, provide users with the best after-sales points in combination with the spare parts to be sold, and build a corresponding navigation route.

[0049] It should be further explained that, in the specific implementation process, the process of obtaining the user's vehicle data and building the corresponding vehicle after-sales model includes:

[0050] Collect various vehicle data of users, which are used to describe the basic information, performance parameters, usage status, after-sales records, and spare parts information of the vehicle;

[0051] The basic information includes vehicle model, brand name, frame number, engine number, purchase date, vehicle type, etc. The performance parameters include vehicle deadweight and load, construction speed, bearing weight, axle configuration and axle column number, braking form, etc. The usage status includes mileage, usage nature, wear and tear, service life, etc.;

[0052] Use digital twin technology to build a digital twin model of the vehicle based on the collected basic information, performance parameters, and usage conditions, and upload the collected after-sales records and spare parts information to the constructed digital twin model for synchronization to obtain the corresponding vehicle after-sales model;

[0053] The after-sales records include repair date, repair items, maintenance conditions, fault conditions, and spare parts replacement, etc. In the vehicle after-sales model, the real-time status of each spare part of the vehicle can be viewed. The spare parts information includes spare part name, spare part type, spare part material, spare part performance parameters, spare part service life, etc.

[0054] It should be further explained that, in the specific implementation process, the vehicle after-sales model is divided into different model sets, and the process of obtaining corresponding influencing parameter sets according to the spare parts in the same model set includes:

[0055] In an embodiment of the present invention, vehicle after-sales models of different users are obtained, and the vehicle after-sales models include different components, such as a battery system, a drive system, a control system, a chassis system, a charging system, an auxiliary system, an air conditioning system, etc.;

[0056] Each component contains specific spare parts. The present invention takes each specific spare part as a benchmark, and includes all vehicle aftermarket models containing the same spare part into the same set, and marks them as the model set of the spare part.

[0057] The common parts of the same model set are used as the analysis parts of the model set, and the analysis parts belonging to different vehicle aftermarket models in the same model set are compared. The analysis parts only refer to their functions, not specific brands;

[0058] Obtain the replacement records of the analyzed parts in the after-sales model of a single vehicle in the model set, and take the replacement time corresponding to each replacement record as an analysis node, obtain the maintenance records and repair records between adjacent analysis nodes, and take the maintenance time and repair time corresponding to each maintenance record and repair record as an analysis sub-node;

[0059] Include the analysis sub-nodes between any two adjacent analysis nodes into an analysis set, obtain the total number of analysis sub-nodes in each analysis set, record it as the number of nodes, obtain the time interval between any two adjacent analysis sub-nodes in each analysis set, record it as the node interval, number the analysis sub-nodes, and bind the node interval between each analysis sub-node and its previous analysis sub-node;

[0060] The mileage corresponding to each analysis sub-node is obtained, and the mileage interval corresponding to each node interval is obtained. The influencing parameter set includes the number of nodes in each analysis set and the node interval and mileage interval of each analysis sub-node. The same method is adopted to obtain the influencing parameter set of the analysis parts and components in each model set.

[0061] It should be further explained that, in the specific implementation process, the process of obtaining the after-sales degree of spare parts according to the influencing parameter set includes:

[0062] Taking any spare parts influencing parameter set as an example, the influencing parameter set includes the number of nodes, node intervals, and mileage intervals of all analysis sets of different vehicle after-sales models in the model set. Taking any analysis set as an example, the number of nodes, node intervals, and mileage intervals are marked as n, S, and i , L i , where i=1, 2, ..., n, and obtain the local after-sales degree of the analysis set, denoted as R b ;

[0063]

[0064] in, is a preset fixed parameter. The same method is used to obtain the local after-sales degree of each analysis set in the influencing parameter set, which is recorded as R bj , where j = 1, 2, ..., m, and m is the total number of analysis sets in the influencing parameter set. The comprehensive after-sales degree of the spare parts is obtained, denoted as R z ;

[0065]

[0066] The same method is adopted to obtain the comprehensive after-sales degree of different spare parts respectively. The comprehensive after-sales degree is used to reflect that the spare part needs to be replaced after reaching this value. The after-sales degree includes partial after-sales degree and comprehensive after-sales degree.

[0067] It should be further explained that, in the specific implementation process, the process of constructing the after-sales evaluation model of spare parts according to different influencing parameter sets and their corresponding after-sales degrees includes:

[0068] Taking the influencing parameter set of any spare parts as an example, an after-sales evaluation set is generated according to the number of nodes, node interval, mileage interval and corresponding local after-sales degree of different analysis sets in the influencing parameter set, and the obtained after-sales evaluation set is divided into a training set and a test set;

[0069] Construct a convolutional neural network, use different numbers of nodes, node intervals, and mileage intervals in the training set as input data of the convolutional neural network, use the corresponding local after-sales degree in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network;

[0070] The initial convolutional neural network is verified using the test set, and the initial convolutional neural network with a test error threshold value that is less than or equal to the preset value is output as the corresponding after-sales evaluation model. The same method is used to obtain the after-sales evaluation model of each spare part.

[0071] The local after-sales degree is obtained based on a complete analysis set, that is, both ends of the analysis set have a replacement record. The after-sales evaluation model is used to obtain the local after-sales degree of an incomplete analysis set, that is, the analysis set only has the last replacement record and has not yet been replaced.

[0072] It should be further explained that, in the specific implementation process, the process of obtaining the user's after-sales degree set, obtaining the spare parts to be sold according to the after-sales degree set, and generating the corresponding after-sales signal includes:

[0073] Obtaining the current analysis set of each spare part in the user's vehicle after-sales model, wherein the current analysis set refers to all repair records and maintenance records from the latest replacement record to the present;

[0074] The number of nodes, node intervals, and mileage intervals in each current analysis set are input into the corresponding after-sales evaluation model, and the after-sales evaluation model is used to output the corresponding local after-sales degree, which is recorded as the evaluated after-sales degree. The evaluated after-sales degree of each spare part is included in the user's after-sales degree set;

[0075] Taking any spare part as an example, according to the comprehensive after-sales degree of the spare part and the current analysis set, the corresponding after-sales degree threshold is set for it, and the mean of the number of nodes in each analysis set in the influencing parameter set of the spare part is taken as the standard node number, recorded as Q z ;

[0076] Get the number of nodes in the current analysis set of the spare part, recorded as Q d , combined with comprehensive after-sales service z Get the after-sales threshold R of the spare part y ;

[0077]

[0078] The evaluation of the after-sales degree of this spare part is R p and after-sales threshold R y For comparison, if R p <R y , no operation is performed on it. If Rp ≥R y , then mark it as aftermarket spare parts;

[0079] The same method is adopted to obtain the after-sales degree threshold of each spare part, and obtain the spare parts to be sold, generate corresponding after-sales signals according to the obtained spare parts to be sold, and feed them back to the user. The after-sales signal is used to remind the user to provide after-sales service for the spare parts to be sold in time.

[0080] It should be further explained that, in the specific implementation process, the process of obtaining the geographic data of the after-sales points and constructing the corresponding after-sales distribution map includes:

[0081] The after-sales point refers to a business place that can provide after-sales service for vehicles, and the geographical data of all after-sales points in different regions are obtained, and the geographical data includes the geographical location of each after-sales point (represented by latitude and longitude) and the traffic route conditions in different regions;

[0082] GIS technology is used to construct a distribution map of after-sales points in different areas based on the collected geographic data, which is recorded as an after-sales distribution map. In the after-sales distribution map, each after-sales point in different areas can be viewed separately. At this time, the after-sales distribution map only includes the geographical location and traffic routes of the after-sales points, and does not include other subsequent data.

[0083] It should be further explained that, in the specific implementation process, the process of obtaining after-sales data of after-sales points, providing users with the best after-sales points in combination with spare parts to be sold, and constructing corresponding navigation routes includes:

[0084] Obtain after-sales data of all after-sales outlets in different regions, wherein the after-sales data refers to the spare parts that can be provided by each after-sales outlet and their corresponding after-sales prices, and the after-sales outlet that contains the spare parts to be provided by the user and has the lowest after-sales price is regarded as the optimal after-sales outlet;

[0085] The user's vehicle location is obtained, and the shortest navigation route is generated between the vehicle location and the optimal after-sales point in the after-sales distribution map. The generated navigation route is fed back to the user, and the user can choose to go there by himself or have door-to-door service.

[0086] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A new energy vehicle after-sales data management system based on big data, characterized in that: Includes the following modules: Data collection module, used to obtain the user's vehicle data and build the corresponding vehicle after-sales model; A data analysis module is used to divide the vehicle after-sales model into different model sets, obtain corresponding influencing parameter sets according to the spare parts in the same model set, and obtain the after-sales degree of the spare parts according to the influencing parameter sets; The after-sales evaluation module is used to build an after-sales evaluation model for spare parts based on different influencing parameter sets and their corresponding after-sales degrees, obtain the user's after-sales degree set, obtain the spare parts to be sold based on the after-sales degree set, and generate corresponding after-sales signals; The after-sales selection module is used to obtain the geographic data of after-sales points, build the corresponding after-sales distribution map, obtain the after-sales data of after-sales points, provide users with the best after-sales points in combination with the spare parts to be sold, and build the corresponding navigation route; The process of obtaining vehicle data and building a vehicle after-sales model includes: Collect various vehicle data of users, including basic information, performance parameters, usage status, after-sales records, and spare parts information; Use digital twin technology to build a digital twin model of the vehicle based on basic information, performance parameters, and usage conditions, and upload after-sales records and spare parts information to the digital twin model for synchronization to obtain the vehicle after-sales model; The process of dividing the vehicle after-sales model into different model sets and obtaining the corresponding influencing parameter sets includes: The vehicle after-sales model includes different components, each component includes different spare parts, and the vehicle after-sales models including the same spare parts are included in the same model set; The parts common to the same model set are used as the analysis parts of the model set, the replacement records and analysis nodes of the analysis parts in the after-sales model of a single vehicle in the model set are obtained, and the maintenance records and repair records of adjacent analysis nodes and their corresponding analysis sub-nodes are obtained; Include the analysis sub-nodes between any two adjacent analysis nodes into an analysis set, and obtain the number of nodes in each analysis set and their corresponding node intervals and mileage intervals; The influencing parameter set includes the number of nodes in each analysis set in different vehicle after-sales models in the same model set and their corresponding node intervals and mileage intervals, and the analysis parts and influencing parameter sets of each model set are obtained respectively; The process of obtaining the after-sales degree of spare parts based on the influencing parameter set includes: According to the number of nodes n and node interval S in a single analysis set in the influencing parameter set i , Mileage interval L i Get the local after-sales degree R of the analysis set b , i=1, 2, ..., n; is a preset fixed parameter, according to the local after-sales degree R of each analysis set in the same influencing parameter set bj , obtain the comprehensive after-sales degree R of the analyzed parts corresponding to the influencing parameter set z , j = 1, 2, ..., m, m is the total number of analysis sets in the influencing parameter set, The comprehensive after-sales degree of the analyzed parts and components corresponding to different influencing parameter sets are obtained respectively, and the after-sales degree is divided into a local after-sales degree and a comprehensive after-sales degree.

2. According to the big data-based new energy vehicle after-sales data management system of claim 1, it is characterized in that: The process of building a post-sales evaluation model for spare parts includes: Generate an after-sales evaluation set according to the number of nodes, node interval, mileage interval and corresponding local after-sales degree of different analysis sets in the influencing parameter set of a single spare part, and divide the after-sales evaluation set into a training set and a test set; Construct a convolutional neural network, use different numbers of nodes, node intervals, and mileage intervals in the training set as input data of the convolutional neural network, use the corresponding local after-sales degree in the training set as output data of the convolutional neural network, and train the convolutional neural network to obtain an initial convolutional neural network; The test set is used to verify the initial convolutional neural network model, and the initial convolutional neural network with a preset test error threshold is output as the after-sales evaluation model of a single spare part, and the after-sales evaluation models of each spare part are obtained respectively.

3. The after-sales data management system for new energy vehicles based on big data according to claim 2 is characterized in that: The process of obtaining the after-sales service set and obtaining the spare parts to be sold includes: Obtaining the current analysis set of each spare part in the user's vehicle after-sales model, wherein the current analysis set refers to all repair records and maintenance records from the latest replacement record to the present; Input the number of nodes, node intervals, and mileage intervals in each current analysis set into the corresponding after-sales evaluation model to obtain the corresponding evaluated after-sales degree, and include the evaluated after-sales degree of each spare part into the user's after-sales degree set; According to the comprehensive after-sales degree of a single spare part and the current analysis set, a corresponding after-sales degree threshold is set for it, and the mean number of nodes in each analysis set in the impact parameter set of the single spare part is taken as the standard node number Q z ; Get the number of nodes Q in the current analysis set of this single component d , combined with its comprehensive after-sales service z Get the after-sales threshold R of the single spare part y ; The evaluation of the after-sales degree of this single spare part is R p and after-sales threshold R y Comparison is performed to obtain corresponding spare parts to be sold, after-sales degree thresholds of various spare parts and their spare parts to be sold are obtained respectively, and corresponding after-sales signals are generated for feedback.

4. The after-sales data management system for new energy vehicles based on big data according to claim 3 is characterized in that: The process of obtaining geographic data of after-sales points and constructing an after-sales distribution map includes: The after-sales point refers to a business place that can provide after-sales service for vehicles. The geographic data of all after-sales points in different regions are obtained, including the geographical location of each after-sales point and the traffic routes in different regions. GIS technology is used to construct after-sales distribution maps of different regions based on geographic data.

5. The after-sales data management system for new energy vehicles based on big data according to claim 4 is characterized in that: The process of obtaining after-sales data of after-sales points and providing the best after-sales points includes: Obtain after-sales data of all after-sales outlets in different regions, including spare parts that can be provided by each after-sales outlet and their corresponding after-sales prices, and select the after-sales outlet that contains the user's spare parts to be provided and has the lowest after-sales price as the optimal after-sales outlet; The user's vehicle location is obtained, the shortest navigation route is generated between the vehicle location and the optimal after-sales point in the after-sales distribution map, and the generated navigation route is fed back to the user.

Images